A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
Thinking machines: A survey of llm based reasoning strategies
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
verdicts
UNVERDICTED 5representative citing papers
Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.
A neuro-symbolic system pairing LLMs for symbolic reasoning with neural delta controllers for execution delivers over 70% step reduction and up to 8.83x speedup in language-guided planar object manipulation while remaining robust to LLM quality.
StaRPO improves LLM reasoning by adding autocorrelation function and path efficiency stability metrics to RL policy optimization, yielding higher accuracy and fewer logic errors on reasoning benchmarks.
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
citing papers explorer
-
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
-
One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging
Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.
-
Neuro-Symbolic Control with Large Language Models for Language-Guided Spatial Tasks
A neuro-symbolic system pairing LLMs for symbolic reasoning with neural delta controllers for execution delivers over 70% step reduction and up to 8.83x speedup in language-guided planar object manipulation while remaining robust to LLM quality.
-
StaRPO: Stability-Augmented Reinforcement Policy Optimization
StaRPO improves LLM reasoning by adding autocorrelation function and path efficiency stability metrics to RL policy optimization, yielding higher accuracy and fewer logic errors on reasoning benchmarks.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.